mlsanityData to 7 Oct 2026

Towards Generalization and Simplicity in Continuous Control

arXiv 1703.02660 ↗First posted 8 Mar 2017cs.LG cs.AI cs.ROcited by 65

Not on the map. Why?

Abstract (arXiv)

This work shows that policies with simple linear and RBF parameterizations can be trained to solve a variety of continuous control tasks, including the OpenAI gym benchmarks. The performance of these trained policies are competitive with state of the art results, obtained with more elaborate parameterizations such as fully connected neural networks. Furthermore, existing training and testing scenarios are shown to be very limited and prone to over-fitting, thus giving rise to only trajectory-centric policies. Training with a diverse initial state distribution is shown to produce more global policies with better generalization. This allows for interactive control scenarios where the system recovers from large on-line perturbations; as shown in the supplementary video.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 2; 2020: 2; 2021: 22; 2022: 9; 2023: 14; 2024: 9; 2025: 4; 2026: 3.

65 papers.

Sort:

By area:

  1. 2020MOReL : Model-Based Offline Reinforcement Learningcited by 582
  2. 2022The Unsurprising Effectiveness of Pre-Trained Vision Models for Controlcited by 155
  3. 2021The Surprising Effectiveness of Representation Learning for Visual Imitationcited by 149
  4. 2021Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learningcited by 123
  5. 2021Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPscited by 115
  6. 2021Decoupling Value and Policy for Generalization in Reinforcement Learningcited by 81
  7. 2022Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?cited by 70
  8. 2023XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAXcited by 54
  9. 2021MobILE: Model-Based Imitation Learning From Observation Alonecited by 44
  10. 2021SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policiescited by 42
  11. 2021Instabilities of Offline RL with Pre-Trained Neural Representationcited by 38
  12. 2019An Optimistic Perspective on Offline Reinforcement Learningcited by 37
38 more
  1. 2024Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applicationscited by 34
  2. 2023On the Importance of Exploration for Generalization in Reinforcement Learningcited by 30
  3. 2021Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environmentscited by 28
  4. 2023The Generalization Gap in Offline Reinforcement Learningcited by 25
  5. 2022Investigating the Properties of Neural Network Representations in Reinforcement Learningcited by 24
  6. 2024SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learningcited by 24
  7. 2023In-Context Reinforcement Learning for Variable Action Spacescited by 23
  8. 2023Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updatescited by 20
  9. 2021When Is Generalizable Reinforcement Learning Tractable?cited by 19
  10. 2021Policy Gradient Methods Find the Nash Equilibrium in N-player General-sum Linear-quadratic Gamescited by 19
  11. 2021Policy Search for Model Predictive Control with Application to Agile Drone Flightcited by 17
  12. 2021Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learningcited by 15
  13. 2022Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributionscited by 15
  14. 2023Causal Semantic Communication for Digital Twins: A Generalizable Imitation Learning Approachcited by 14
  15. 2023Memory-Consistent Neural Networks for Imitation Learningcited by 14
  16. 2021Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixturecited by 12
  17. 2022REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfercited by 12
  18. 2024Locality Sensitive Sparse Encoding for Learning World Models Onlinecited by 12
  19. 2022Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Samplingcited by 10
  20. 2022Local Feature Swapping for Generalization in Reinforcement Learningcited by 9
  21. 2021Measuring Progress in Deep Reinforcement Learning Sample Efficiencycited by 8
  22. 2022HERD: Continuous Human-to-Robot Evolution for Learning from Human Demonstrationcited by 8
  23. 2019Randomized Adversarial Imitation Learning for Autonomous Drivingcited by 6
  24. 2021Provable Regret Bounds for Deep Online Learning and Controlcited by 6
  25. 2021Koopman Spectrum Nonlinear Regulators and Efficient Online Learningcited by 5
  26. 2021Model-Free μ Synthesis via Adversarial Reinforcement Learningcited by 5
  27. 2023Efficiently Learning the Graph for Semi-supervised Learningcited by 5
  28. 2023Measuring and Mitigating Interference in Reinforcement Learningcited by 5
  29. 2021The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Expertscited by 4
  30. 2023Policy Gradient Algorithms Implicitly Optimize by Continuationcited by 4
  31. 2020Adversarial Imitation Learning via Random Searchcited by 3
  32. 2024Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfercited by 3
  33. 2025Provable Zero-Shot Generalization in Offline Reinforcement Learningcited by 3
  34. 2021Online Algorithms and Policies Using Adaptive and Machine Learning Approachescited by 2
  35. 2023Machine Learning Meets Advanced Robotic Manipulationcited by 2
  36. 2024Solving Deep Reinforcement Learning Tasks with Evolution Strategies and Linear Policy Networkscited by 2
  37. 2024A learning-based approach to stochastic optimal control under reach-avoid constraintcited by 2
  38. 2021Sparse Attention Guided Dynamic Value Estimation for Single-Task Multi-Scene Reinforcement Learningcited by 1

50 most cited of 65 All 65 (JSON)